Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.5273. Min Act: -0.0001

Data Index: 794921 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4162. Min Act: -0.0001

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4183. Min Act: -0.0001

Data Index: 781946 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.4396. Min Act: -0.0001

Data Index: 253981 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3484. Min Act: -0.0001

Data Index: 470422 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3232. Min Act: -0.0001

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3726. Min Act: -0.0001

Data Index: 694890 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3373. Min Act: -0.0001

Data Index: 1157047 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3271. Min Act: -0.0001

Data Index: 20864 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3015. Min Act: -0.0000

Data Index: 445277 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.2885. Min Act: -0.0000

Data Index: 125534 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.2966. Min Act: -0.0000

Data Index: 559552 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.2778. Min Act: -0.0001

Data Index: 189440 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3153. Min Act: -0.0001

Data Index: 136843 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3043. Min Act: -0.0001

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.2875. Min Act: -0.0001

Data Index: 1057171 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1059924 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3087. Min Act: -0.0000

Data Index: 850167 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.2608. Min Act: -0.0000

Data Index: 490443 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.5273. Min Range: -0.5273

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1176830 (C4 (Web Text))

Max Activating Token Index: 947